Matthew Thompson
@thompson.gr
Architect/Engineer and Independent Researcher.
Finishing Master in DS and AI. Interested in Meta-Reasoning.
Researching in-context reasoning for ML-Agents via Cohere Labs, doing some data annotation, and learning more about rational agents.
Finishing Master in DS and AI. Interested in Meta-Reasoning.
Researching in-context reasoning for ML-Agents via Cohere Labs, doing some data annotation, and learning more about rational agents.
Consciousness - is it important for AI?: https://matt.thompson.gr/2025/09/10/consciousness-is-it-important-for.html
September 10, 2025 at 6:02 AM
Consciousness - is it important for AI?: https://matt.thompson.gr/2025/09/10/consciousness-is-it-important-for.html
Functional Information - measuring evolution and AGI?: https://matt.thompson.gr/2025/08/14/functional-information-measuring-evolution-and.html
Functional Information: a way to represent information that has come to be useful over time. That is information that provides a function for itself or a...
Functional Information: a way to represent information that has come to be useful over time. That is information that provides a function for itself or a...
August 14, 2025 at 2:53 PM
Functional Information - measuring evolution and AGI?: https://matt.thompson.gr/2025/08/14/functional-information-measuring-evolution-and.html
Functional Information: a way to represent information that has come to be useful over time. That is information that provides a function for itself or a...
Functional Information: a way to represent information that has come to be useful over time. That is information that provides a function for itself or a...
Double Split Experiment lecture from 1964 (remastered): https://matt.thompson.gr/2025/08/12/double-split-experiment-lecture-from.html
Remastered broadcast of a 1964 lecture by Richard Feynman on the Double Split experiment. Finished with a call to action on having open priors to evidence we see ...
Remastered broadcast of a 1964 lecture by Richard Feynman on the Double Split experiment. Finished with a call to action on having open priors to evidence we see ...
August 11, 2025 at 11:11 PM
Double Split Experiment lecture from 1964 (remastered): https://matt.thompson.gr/2025/08/12/double-split-experiment-lecture-from.html
Remastered broadcast of a 1964 lecture by Richard Feynman on the Double Split experiment. Finished with a call to action on having open priors to evidence we see ...
Remastered broadcast of a 1964 lecture by Richard Feynman on the Double Split experiment. Finished with a call to action on having open priors to evidence we see ...
Interesting presentation on the downfall of the Bronze Age Civilization around Egypt, Greece, and the Eastern Mediterranean.
.video-wrapper {
position: relative;
padding-bottom: 56.25%;
height: 0;
max-width... https://matt.thompson.gr/2025/07/28/interesting-presentation-on-the-downfall.html
.video-wrapper {
position: relative;
padding-bottom: 56.25%;
height: 0;
max-width... https://matt.thompson.gr/2025/07/28/interesting-presentation-on-the-downfall.html
July 28, 2025 at 11:27 AM
Interesting presentation on the downfall of the Bronze Age Civilization around Egypt, Greece, and the Eastern Mediterranean.
.video-wrapper {
position: relative;
padding-bottom: 56.25%;
height: 0;
max-width... https://matt.thompson.gr/2025/07/28/interesting-presentation-on-the-downfall.html
.video-wrapper {
position: relative;
padding-bottom: 56.25%;
height: 0;
max-width... https://matt.thompson.gr/2025/07/28/interesting-presentation-on-the-downfall.html
Instructions for using Micro.blog VS Code extension (alpha): https://matt.thompson.gr/2025/07/19/instructions-for-using-microblog-vs.html
July 19, 2025 at 12:40 PM
Instructions for using Micro.blog VS Code extension (alpha): https://matt.thompson.gr/2025/07/19/instructions-for-using-microblog-vs.html
Can LLMs do Critical Thinking? Of course not. Can an AI system think clearly? Why not?: https://matt.thompson.gr/2025/06/29/can-llms-do-critical-thinking.html
June 29, 2025 at 9:20 PM
Can LLMs do Critical Thinking? Of course not. Can an AI system think clearly? Why not?: https://matt.thompson.gr/2025/06/29/can-llms-do-critical-thinking.html
The old ‘un still does the job on the MINST Handwritten dataset !
June 28, 2025 at 7:38 AM
The old ‘un still does the job on the MINST Handwritten dataset !
[IA Series 7/n] Building a Self-Consistency LLM-Agent: From PEAS Analysis to Production Code: https://matt.thompson.gr/2025/06/26/ia-series-n-building-a.html
Building a Self-Consistency LLM-Agent: From PEAS Analysis to Production Code - a guide to designing an LLM-based agent.
Building a Self-Consistency LLM-Agent: From PEAS Analysis to Production Code - a guide to designing an LLM-based agent.
June 26, 2025 at 3:20 PM
[IA Series 7/n] Building a Self-Consistency LLM-Agent: From PEAS Analysis to Production Code: https://matt.thompson.gr/2025/06/26/ia-series-n-building-a.html
Building a Self-Consistency LLM-Agent: From PEAS Analysis to Production Code - a guide to designing an LLM-based agent.
Building a Self-Consistency LLM-Agent: From PEAS Analysis to Production Code - a guide to designing an LLM-based agent.
A refreshing AI-en-Provence 🍦
June 23, 2025 at 3:42 PM
A refreshing AI-en-Provence 🍦
AI-en-Provence 🤓😂✌🏼✌🏼✌🏼
June 22, 2025 at 10:16 AM
AI-en-Provence 🤓😂✌🏼✌🏼✌🏼
[IA Series 6/n] A Bayesian Learning Agent: Bayes Theorem and Intelligent Agents: https://matt.thompson.gr/2025/06/18/ia-series-n-an-evidencebased.html
The article discusses how to implement Bayes Theorem in a learning agent that updates its beliefs about an environment based on new evidence, ill...
The article discusses how to implement Bayes Theorem in a learning agent that updates its beliefs about an environment based on new evidence, ill...
June 19, 2025 at 4:45 AM
[IA Series 6/n] A Bayesian Learning Agent: Bayes Theorem and Intelligent Agents: https://matt.thompson.gr/2025/06/18/ia-series-n-an-evidencebased.html
The article discusses how to implement Bayes Theorem in a learning agent that updates its beliefs about an environment based on new evidence, ill...
The article discusses how to implement Bayes Theorem in a learning agent that updates its beliefs about an environment based on new evidence, ill...
It is not reasoning: https://matt.thompson.gr/2025/06/05/llms-output-is-not-reasoning.html
Reasoning vs Stream of Consciousness - the output of a transformer is not reasoned in the way we think it is.
Reasoning vs Stream of Consciousness - the output of a transformer is not reasoned in the way we think it is.
June 7, 2025 at 7:46 PM
It is not reasoning: https://matt.thompson.gr/2025/06/05/llms-output-is-not-reasoning.html
Reasoning vs Stream of Consciousness - the output of a transformer is not reasoned in the way we think it is.
Reasoning vs Stream of Consciousness - the output of a transformer is not reasoned in the way we think it is.
[Knowledge Series 1/n] Introspection and the cusp of not knowing: https://matt.thompson.gr/2025/06/04/knowledge-series-n-introspection-and.html
Post silent meditation retreat reflections on knowledge.
Post silent meditation retreat reflections on knowledge.
June 4, 2025 at 11:01 AM
[Knowledge Series 1/n] Introspection and the cusp of not knowing: https://matt.thompson.gr/2025/06/04/knowledge-series-n-introspection-and.html
Post silent meditation retreat reflections on knowledge.
Post silent meditation retreat reflections on knowledge.
[IA Series 5/n] The Evolution from Logic to Probability to Deep Learning: A course correction to Transformers: https://matt.thompson.gr/2025/05/20/ia-series-n-the-evolution.html
May 20, 2025 at 4:28 PM
[IA Series 5/n] The Evolution from Logic to Probability to Deep Learning: A course correction to Transformers: https://matt.thompson.gr/2025/05/20/ia-series-n-the-evolution.html
[IA Series 4/n] A Big Question: Why Study Logic in a World of Probabilistic AI?: https://matt.thompson.gr/2025/05/19/ia-series-n-why-study.html
May 19, 2025 at 6:42 PM
[IA Series 4/n] A Big Question: Why Study Logic in a World of Probabilistic AI?: https://matt.thompson.gr/2025/05/19/ia-series-n-why-study.html
[IA Series 3/n] Intelligent Agents Term Sheet: https://matt.thompson.gr/2025/05/16/ia-series-n-intelligent-agents.html
May 16, 2025 at 8:35 AM
[IA Series 3/n] Intelligent Agents Term Sheet: https://matt.thompson.gr/2025/05/16/ia-series-n-intelligent-agents.html
Notes and links on SVMs (WIP): https://matt.thompson.gr/2025/04/26/notes-and-links-on-svms.html
April 26, 2025 at 8:47 AM
Notes and links on SVMs (WIP): https://matt.thompson.gr/2025/04/26/notes-and-links-on-svms.html
[IA Series 2/n] Search Algorithms and Intelligent Agents: https://matt.thompson.gr/2025/04/24/ia-series-n-search-algorithms.html
The document discusses various search algorithms used by Intelligent Agents for navigating mazes, detailing their types, characteristics, tradeoffs, and implementations.
The document discusses various search algorithms used by Intelligent Agents for navigating mazes, detailing their types, characteristics, tradeoffs, and implementations.
April 24, 2025 at 5:06 PM
[IA Series 2/n] Search Algorithms and Intelligent Agents: https://matt.thompson.gr/2025/04/24/ia-series-n-search-algorithms.html
The document discusses various search algorithms used by Intelligent Agents for navigating mazes, detailing their types, characteristics, tradeoffs, and implementations.
The document discusses various search algorithms used by Intelligent Agents for navigating mazes, detailing their types, characteristics, tradeoffs, and implementations.
[Python Series 1/n] Modern Python Package Management: pipx and uv for Data Scientists: https://matt.thompson.gr/2025/04/19/python-series-n-modern-python.html
April 22, 2025 at 8:44 AM
[Python Series 1/n] Modern Python Package Management: pipx and uv for Data Scientists: https://matt.thompson.gr/2025/04/19/python-series-n-modern-python.html
Dystopia? It's already here and that's OK. Here's why.: https://matt.thompson.gr/2025/04/20/dystopia-its-already-here-and.html
The text reflects on the misuse of technology and ethics in Silicon Valley, highlighting the importance of awareness and compassion amidst current challenges.
The text reflects on the misuse of technology and ethics in Silicon Valley, highlighting the importance of awareness and compassion amidst current challenges.
April 20, 2025 at 6:23 AM
Dystopia? It's already here and that's OK. Here's why.: https://matt.thompson.gr/2025/04/20/dystopia-its-already-here-and.html
The text reflects on the misuse of technology and ethics in Silicon Valley, highlighting the importance of awareness and compassion amidst current challenges.
The text reflects on the misuse of technology and ethics in Silicon Valley, highlighting the importance of awareness and compassion amidst current challenges.
finally found something I wanted to use ChatGPT image generation for! On the fridge and the family loves it, going to be a busy week 👨🏻🌾
April 13, 2025 at 3:43 PM
finally found something I wanted to use ChatGPT image generation for! On the fridge and the family loves it, going to be a busy week 👨🏻🌾
Regularisation: reducing the complexity of a model without compromising accuracy: https://matt.thompson.gr/2025/03/17/regularisation-reducing-the-complexity-of.html
March 17, 2025 at 10:56 AM
Regularisation: reducing the complexity of a model without compromising accuracy: https://matt.thompson.gr/2025/03/17/regularisation-reducing-the-complexity-of.html
[NN Series 4/n] Feature Normalisation: https://matt.thompson.gr/2025/03/06/nn-series-n-feature-normalisation.html
March 6, 2025 at 5:12 PM
[NN Series 4/n] Feature Normalisation: https://matt.thompson.gr/2025/03/06/nn-series-n-feature-normalisation.html